© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 61468
    Prev
    Next
    INDEX
    Explanations

    momentum

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æĦı大
    -0.10
    าà¸ģ
    -0.09
    imony
    -0.09
    mint
    -0.08
    ä¸įåĩºæĿ¥
    -0.08
    ingo
    -0.08
    å¯ĤéĿĻ
    -0.08
    benchmark
    -0.08
    out
    -0.08
    æīĢ以说
    -0.08
    POSITIVE LOGITS
    åįģ足
    0.16
    setter
    0.09
    åħħæ²Ľ
    0.09
    hti
    0.09
    æ°ijå¿ĥ
    0.09
    è¹Ħ
    0.08
    ukan
    0.08
    iel
    0.08
    ä¸ĭæ»ij
    0.08
    alem
    0.08
    Activations Density 0.006%

    No Known Activations